<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: m_krebs</title><link>https://news.ycombinator.com/user?id=m_krebs</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 15 Jun 2026 10:53:15 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=m_krebs" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by m_krebs in "If Claude Fable stops helping you, you'll never know"]]></title><description><![CDATA[
<p>this is probably overstating their abilities at present - I am experimenting with Fable on a completely benign personal application and I am constantly hitting the "cybersecurity and biology topics" guardrail</p>
]]></description><pubDate>Tue, 09 Jun 2026 22:25:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=48468641</link><dc:creator>m_krebs</dc:creator><comments>https://news.ycombinator.com/item?id=48468641</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48468641</guid></item><item><title><![CDATA[New comment by m_krebs in "Evolving OpenAI's Structure"]]></title><description><![CDATA[
<p>"X increased exponentially in the past, therefore it will increase exponentially  in the same way in the future" is fallacious. There is nothing guaranteeing indefinite uncapped growth in capabilities of LLMs. An exponential curve and a sigmoidal curve look the same until a certain point.</p>
]]></description><pubDate>Mon, 05 May 2025 19:09:39 +0000</pubDate><link>https://news.ycombinator.com/item?id=43898360</link><dc:creator>m_krebs</dc:creator><comments>https://news.ycombinator.com/item?id=43898360</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43898360</guid></item></channel></rss>